{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/neural-language-modeling-by-jointly-learning","title":"Neural Language Modeling by Jointly Learning Syntax and Lexicon","arxiv_id":"1711.02013","date":"2017-11-02","proceeding":"ICLR 2018 1","authors":["Yikang Shen","Zhouhan Lin","Chin-wei Huang","Aaron Courville"],"abstract":"We propose a neural language model capable of unsupervised syntactic\nstructure induction. The model leverages the structure information to form\nbetter semantic representations and better language modeling. Standard\nrecurrent neural networks are limited by their structure and fail to\nefficiently use syntactic information. On the other hand, tree-structured\nrecursive networks usually require additional structural supervision at the\ncost of human expert annotation. In this paper, We propose a novel neural\nlanguage model, called the Parsing-Reading-Predict Networks (PRPN), that can\nsimultaneously induce the syntactic structure from unannotated sentences and\nleverage the inferred structure to learn a better language model. In our model,\nthe gradient can be directly back-propagated from the language model loss into\nthe neural parsing network. Experiments show that the proposed model can\ndiscover the underlying syntactic structure and achieve state-of-the-art\nperformance on word/character-level language model tasks.","url_abs":"http://arxiv.org/abs/1711.02013v2","url_pdf":"http://arxiv.org/pdf/1711.02013v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"neural-language-modeling-by-jointly-learning","repo_url":"https://github.com/nyu-mll/PRPN-Analysis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"constituency-grammar-induction","task_name":"Constituency Grammar Induction"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/constituency-grammar-induction-on-ptb","task":"Constituency Grammar Induction","dataset":"PTB Diagnostic ECG Database","model":"PRPN (tuned)","rank_in_archive_order":22,"of":24,"metrics":{"Max F1 (WSJ)":"47.9","Mean F1 (WSJ)":"47.3"},"uses_additional_data":false},{"leaderboard":"/sota/constituency-grammar-induction-on-ptb","task":"Constituency Grammar Induction","dataset":"PTB Diagnostic ECG Database","model":"PRPN","rank_in_archive_order":24,"of":24,"metrics":{"Max F1 (WSJ)":"38.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.02013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.02013"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nyu-mll/PRPN-Analysis","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5cbbab8959d49215","entry":"plot","repo":"nyu-mll/PRPN-Analysis","repo_kind":"listed","path":"hinton.py","file_url":"https://github.com/nyu-mll/PRPN-Analysis/blob/HEAD/hinton.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cbbab8959d49215"}},{"code_sha256_prefix":"8bad1a018e52e629","entry":"repackage_hidden","repo":"nyu-mll/PRPN-Analysis","repo_kind":"listed","path":"main_LM.py","file_url":"https://github.com/nyu-mll/PRPN-Analysis/blob/HEAD/main_LM.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bad1a018e52e629"}},{"code_sha256_prefix":"fd0b027b739c21bd","entry":"softmax","repo":"nyu-mll/PRPN-Analysis","repo_kind":"listed","path":"blocks.py","file_url":"https://github.com/nyu-mll/PRPN-Analysis/blob/HEAD/blocks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd0b027b739c21bd"}},{"code_sha256_prefix":"7322e0cfb5f65e1d","entry":"stick_breaking","repo":"nyu-mll/PRPN-Analysis","repo_kind":"listed","path":"blocks.py","file_url":"https://github.com/nyu-mll/PRPN-Analysis/blob/HEAD/blocks.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7322e0cfb5f65e1d"}},{"code_sha256_prefix":"3694ae0819c608c9","entry":"visual","repo":"nyu-mll/PRPN-Analysis","repo_kind":"listed","path":"hinton.py","file_url":"https://github.com/nyu-mll/PRPN-Analysis/blob/HEAD/hinton.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3694ae0819c608c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}